{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:58:03Z","timestamp":1740099483439,"version":"3.37.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030304898"},{"type":"electronic","value":"9783030304904"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-30490-4_17","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T23:02:47Z","timestamp":1567983767000},"page":"198-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Discriminative Feature Learning for Speech Emotion Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2451-2727","authenticated-orcid":false,"given":"Yuying","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9999-6140","authenticated-orcid":false,"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyi","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danqing","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Neiberg, D., Elenius, K., Laskowski, K.: Emotion recognition in spontaneous speech using GMMs. In: Ninth International Conference on Spoken Language Processing (2006)","DOI":"10.21437\/Interspeech.2006-277"},{"key":"17_CR2","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"TL New","year":"2003","unstructured":"New, T.L., Foo, S.W., De Silva, L.C.: Speech emotion recognition using hidden Markov models. Speech Commun. 41, 603\u2013623 (2003)","journal-title":"Speech Commun."},{"key":"17_CR3","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1109\/TASL.2010.2076804","volume":"19","author":"E Mower","year":"2010","unstructured":"Mower, E., Mataric, M.J., Narayanan, S.: A framework for automatic human emotion classification using emotion profiles. IEEE Trans. Audio Speech Lang. Process. 19, 1057\u20131070 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Stuhlsatz, A., Meyer, C., Eyben, F., et al.: Deep neural networks for acoustic emotion recognition: raising the benchmarks. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5688\u20135691 (2011)","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Han, K., Yu, D., Tashev, I.: Speech emotion recognition using deep neural network and extreme learning machine. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-57"},{"key":"17_CR6","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/978-981-10-3005-5_59","volume-title":"Pattern Recognition","author":"Y Huang","year":"2016","unstructured":"Huang, Y., Hu, M., Yu, X., Wang, T., Yang, C.: Transfer learning of deep neural network for speech emotion recognition. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds.) CCPR 2016. CCIS, vol. 663, pp. 721\u2013729. Springer, Singapore (2016). https:\/\/doi.org\/10.1007\/978-981-10-3005-5_59"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Mower, E., Metallinou, A., Lee, C.C., et al.: Interpreting ambiguous emotional expressions. In: 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, pp. 1\u20138. IEEE (2009)","DOI":"10.1109\/ACII.2009.5349500"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chao, L., Tao, J., Yang, M., Li, Y., et al.: Long short term memory recurrent neural network based encoding method for emotion recognition in video. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2752\u20132756 (2016)","DOI":"10.1109\/ICASSP.2016.7472178"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Ma, X., Wu, Z., Jia, J., et al.: Speech emotion recognition with emotion-pair based framework considering emotion distribution information in dimensional emotion space. In: INTERSPEECH 2017, pp. 1238\u20131242 (2017)","DOI":"10.21437\/Interspeech.2017-619"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Ma, X., Wu, Z., Jia, J., et al.: Emotion recognition from variable-length speech segments using deep learning on spectrograms. In: Proceedings of Interspeech 2018, pp. 3683\u20133687 (2018)","DOI":"10.21437\/Interspeech.2018-2228"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (2018)","DOI":"10.1109\/ICCV.2017.324"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Huang, J., Li, Y., Tao, J., Lian, Z.: Speech emotion recognition from variable-length inputs with triplet loss function. In: Proceedings of Interspeech 2018, pp. 3673\u20133677 (2018)","DOI":"10.21437\/Interspeech.2018-1432"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Lian, Z., Li, Y., Tao, J., et al.: Speech emotion recognition via contrastive loss under siamese networks. In: Proceedings of the Joint Workshop of the 4th Workshop on Affective Social Multimedia Computing and First Multi-Modal Affective Computing of Large-Scale Multimedia Data, pp. 21\u201326. ACM (2018)","DOI":"10.1145\/3267935.3267946"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Li, N., Tuo, D., Su, D., et al.: Deep discriminative embeddings for duration robust speaker verification. In: Proceedings of Interspeech 2018, pp. 2262\u20132266 (2018)","DOI":"10.21437\/Interspeech.2018-1769"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Wang, S., Qian, Y., Yu, K.: Focal KL-divergence based dilated convolutional neural networks for co-channel speaker identification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5339\u20135343. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462620"},{"key":"17_CR16","unstructured":"Bhargava, M., Polzehl, T.: Improving automatic emotion recognition from speech using rhythm and temporal feature. arXiv preprint arXiv:1303.1761 (2013)"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Guo, L., Wang, L., Dang, J., Zhang, L., Guan, H.: A feature fusion method based on extreme learning machine for speech emotion recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2666\u20132670 (2018)","DOI":"10.1109\/ICASSP.2018.8462219"},{"key":"17_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-70772-3_1","volume-title":"Brain Informatics","author":"Y Gao","year":"2017","unstructured":"Gao, Y., Li, B., Wang, N., Zhu, T.: Speech emotion recognition using local and global features. In: Zeng, Y., He, Y., Kotaleski, J.H., Martone, M., Xu, B., Peng, H., Luo, Q. (eds.) BI 2017. LNCS (LNAI), vol. 10654, pp. 3\u201313. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-70772-3_1"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A.: The interspeech 2009 emotion challenge. In: Tenth Annual Conference of the International Speech Communication Association (2009)","DOI":"10.21437\/Interspeech.2009-103"},{"key":"17_CR20","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1109\/TIFS.2018.2833032","volume":"13","author":"X Wu","year":"2018","unstructured":"Wu, X., He, R., Sun, Z., Tan, T.: A light CNN for deep face representation with noisy labels. IEEE Trans. Inf. Forensics Secur. 13, 2884\u20132896 (2018)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Lee, J., Tashev, I.: High-level feature representation using recurrent neural network for speech emotion recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-336"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Text and Time Series"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30490-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T21:28:15Z","timestamp":1664314095000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30490-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304898","9783030304904"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30490-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}